def main(argv):
argparse_usage = (
'fungap.py -g <genome_assembly> -12UA <trans_read_files> '
'-o <output_dir> -a <augustus_species> '
'-s <sister_proteome>')
parser = ArgumentParser(usage=argparse_usage)
parser.add_argument('-o',
'--output_dir',
nargs='?',
default='fungap_out',
help='Output directory (default: fungap_out)')
parser.add_argument('-1',
'--trans_read_1',
nargs='?',
default='',
help='Paired-end read1 "<prefix>_1.fastq"')
parser.add_argument('-2',
'--trans_read_2',
nargs='?',
default='',
help='Paired-end read2 "<prefix>_2.fastq"')
parser.add_argument('-U',
'--trans_read_single',
nargs='?',
default='',
help='Single read "<prefix>_s.fastq"')
parser.add_argument(
'-A',
'--trans_bam',
nargs='?',
default='',
help='BAM file (RNA-seq reads alignment to a genome assembly')
parser.add_argument('-g',
'--genome_assembly',
nargs=1,
required=True,
help='Genome assembly file in FASTA format')
parser.add_argument('-a',
'--augustus_species',
nargs=1,
required=True,
help='AUGUSTUS species')
parser.add_argument('-s',
'--sister_proteome',
nargs=1,
required=True,
help='Sister proteome sequences in .faa')
parser.add_argument('-c',
'--num_cores',
nargs='?',
default=1,
type=int,
help='Number of cores to be used (default: 1)')
parser.add_argument('-v',
'--version',
action='version',
version='%(prog)s {}'.format(__version__))
# Options for non-fungus genome
parser.add_argument(
'--no_braker_fungus',
action='store_true',
help='No --fungus flag in BRAKER for non-fungus genomes')
parser.add_argument(
'--no_jaccard_clip',
action='store_true',
help='No --jaccard_clip flag in Trinity for non-fungus genomes')
parser.add_argument(
'--no_genemark_fungus',
action='store_true',
help='No --fungus flag in GeneMark for non-fungus genomes')
parser.add_argument('-M',
'--max_intron',
nargs='?',
default=2000,
type=int,
help='Max intron length (Default: 2000 bp)')
args = parser.parse_args()
output_dir = os.path.abspath(args.output_dir)
trans_read_1 = args.trans_read_1
trans_read_2 = args.trans_read_2
trans_read_single = args.trans_read_single
trans_bam = args.trans_bam
genome_assembly = os.path.abspath(args.genome_assembly[0])
augustus_species = args.augustus_species[0]
sister_proteome = os.path.abspath(args.sister_proteome[0])
num_cores = args.num_cores
max_intron = args.max_intron
# For non-fungus genomes
if args.no_braker_fungus:
no_braker_fungus = ''
else:
no_braker_fungus = '--fungus'
if args.no_jaccard_clip:
no_jaccard_clip = ''
else:
no_jaccard_clip = '--jaccard_clip'
if args.no_genemark_fungus:
no_genemark_fungus = ''
else:
no_genemark_fungus = '--gmes_fungus'
# Create nessasary dirs
create_dir(output_dir)
# Set logging
log_file = os.path.join(output_dir, 'logs', 'fungap.log')
global logger_time, logger_txt
logger_time, logger_txt = set_logging(log_file)
logger_txt.debug('\n============ New Run {} ============'.format(
datetime.now()))
# Run functions :) Slow is as good as Fast
trans_read_files = check_inputs(trans_read_1, trans_read_2,
trans_read_single, trans_bam,
genome_assembly, sister_proteome)
trans_bams = run_hisat2(genome_assembly, trans_read_files, output_dir,
num_cores, max_intron)
trinity_asms = run_trinity(trans_bams, output_dir, num_cores,
no_jaccard_clip, max_intron)
repeat_model_file = run_repeat_modeler(genome_assembly, output_dir,
num_cores)
maker_gff3s, maker_faas = run_maker(genome_assembly, output_dir,
augustus_species, sister_proteome,
num_cores, repeat_model_file,
trinity_asms, no_genemark_fungus)
# Get masked assembly
masked_assembly = os.path.join(output_dir, 'maker_out',
'masked_assembly.fasta')
# Run Augustus
augustus_gff3, augustus_faa = run_augustus(masked_assembly, output_dir,
augustus_species)
# Run Braker1
braker1_gff3s, braker1_faas = run_braker1(masked_assembly, trans_bams,
output_dir, num_cores,
no_braker_fungus)
# Run BUSCO on each gene models
faa_files = [augustus_faa] + maker_faas + braker1_faas
for faa_file in faa_files:
run_busco(faa_file, output_dir, num_cores)
busco_out_dir = os.path.join(output_dir, 'busco_out')
# Get protein nr by removing identical proteins
nr_prot_file, nr_prot_mapping_file = make_nr_prot(faa_files, output_dir)
# Run BLASTp with nr prot file
blastp_output = run_blastp(nr_prot_file, output_dir, sister_proteome,
num_cores)
# Run Pfam_scan with nr prot file
pfam_scan_out = run_pfam_scan(nr_prot_file, output_dir, num_cores)
# Concatenate all transcripts files
gene_filtering_dir = os.path.join(output_dir, 'gene_filtering')
trinity_asm = os.path.join(gene_filtering_dir, 'trinity_transcripts.fna')
command = 'cat {} > {}'.format(' '.join(trinity_asms), trinity_asm)
logger_time.debug('Create transcript')
logger_txt.debug('[Run] {}'.format(command))
os.system(command)
gff3_files = [augustus_gff3] + maker_gff3s + braker1_gff3s
blastn_out_files = []
for gff3_file in gff3_files:
transcript_file = make_transcripts(genome_assembly, gff3_file)
blastn_out_file = run_blastn(transcript_file, trinity_asm, output_dir)
blastn_out_files.append(blastn_out_file)
# Import BLAST, BUSCO and Pfam score
blastp_dict = import_blastp(blastp_output, nr_prot_mapping_file)
busco_dict = import_busco(busco_out_dir, output_dir)
pfam_dict = import_pfam(pfam_scan_out, nr_prot_mapping_file)
blastn_dict = import_blastn(blastn_out_files, output_dir)
# Catch bad genes
bad_dict = catch_bad_genes(gff3_files, genome_assembly, output_dir)
filter_gff3s(genome_assembly, gff3_files, blastp_dict, busco_dict,
pfam_dict, blastn_dict, bad_dict, nr_prot_file,
nr_prot_mapping_file, output_dir)
gff3_postprocess(genome_assembly, output_dir)
# Copy output files
copy_output(output_dir)
# Create markdown
create_markdown(genome_assembly, output_dir, trans_bams, trinity_asms)
def getInput(player):
prefix = "{} (Player {})".format(player.name, player.number)
inp = input("{}: Please input 'Rock', 'Paper' or 'Scissors': ".format(prefix)).lower()
if inp not in ["rock", "paper", "scissors"]:
print("{}: Try again.".format(prefix))
getInput(player)
return inp
while True:
p1_inp = getInput(player1)
sys("cls")
p2_inp = getInput(player2)
winner = check_inputs(player1, player2, p1_inp, p2_inp)
if winner == "p1": player1.matches_won += 1
elif winner == "p2": player2.matches_won += 1
try_again = input("Do you want to try again or both player's statistics? Enter 'Yes' to try again, 'viewstats' to view your statistics and anything else to exit. ").lower()
if try_again == "yes":
print("Starting a new game!")
continue
elif try_again == "viewstats":
date1 = datetime.fromtimestamp(started)
date2 = datetime.fromtimestamp(unixtime())
rd = relativedelta(date2, date1)
print("-== STATISTICS ==-\nPlayer 1 ({}): Won {} games.\n\nPlayer 2 ({}): Won {} games.\n\nPlayed for: {} years, {} months, {} days, {} hours, {} minutes and {} seconds.".format(player1.name, player1.matches_won, player2.name, player2.matches_won, rd.years, rd.months, rd.days, rd.hours, rd.minutes, rd.seconds))
new_try_again = input("Do you want to go back to playing now, or exit? Enter 'Yes' to try again, and anything else to exit. ").lower()
from passengers import Passengers
from traxi import Traxi
from check_inputs import check_inputs
if __name__ == "__main__":
check_inputs()
p = Passengers()
t = Traxi()
while True:
new_passenger = p.generate()
t.manage(new_passenger)
def main(argv):
argparse_usage = (
'fungap.py -g <genome_assembly> -12UA <trans_read_files> '
'-o <output_dir> -p <project_name> -a <augustus_species> '
'-O <org_id> -s <sister_proteome>')
parser = ArgumentParser(usage=argparse_usage)
parser.add_argument("-o",
"--output_dir",
dest="output_dir",
nargs=1,
help="Output directory (default: 'fungap_out')")
parser.add_argument(
"-1",
"--trans_read_1",
dest="trans_read_1",
nargs='?',
help=('Paired-end read1 "<prefix>_1.fastq" <prefix> may not '
'contain "_" character'))
parser.add_argument(
"-2",
"--trans_read_2",
dest="trans_read_2",
nargs='?',
help=('Paired-end read2 "<prefix>_2.fastq" <prefix> may not '
'contain "_" character'))
parser.add_argument(
"-U",
"--trans_read_single",
dest="trans_read_single",
nargs='?',
help=('Single read "<prefix>_s.fastq" <prefix> may not '
'contain "_" character'))
parser.add_argument(
"-A",
"--trans_bam",
dest="trans_bam",
nargs='?',
help='BAM file (RNA-seq reads alignment onto a genome assembly')
parser.add_argument(
"-p",
"--project_name",
dest="project_name",
nargs=1,
help="Project name without space. e.g. Mag (default: 'project')")
parser.add_argument("-g",
"--genome_assembly",
dest="genome_assembly",
nargs=1,
help="Genome assembly file in FASTA format")
parser.add_argument("-a",
"--augustus_species",
dest="augustus_species",
nargs=1,
help="AUGUSTUS species")
parser.add_argument(
"-O",
"--org_id",
dest="org_id",
nargs=1,
help=(
"Organism ID. E.g. Hypma for Hypsizygus marmoreus (default: 'Gene')"
))
parser.add_argument("-s",
"--sister_proteome",
dest="sister_proteome",
nargs=1,
help="Sister proteome sequences in .faa")
parser.add_argument("-c",
"--num_cores",
dest="num_cores",
nargs=1,
help="Number of cores to be used (default: 1)")
parser.add_argument(
"-H",
"--with_hisat2",
dest="with_hisat2",
nargs='?',
help="User-defined Hisat2 installation path (binary directory)")
parser.add_argument(
"-t",
"--with_trinity",
dest="with_trinity",
nargs='?',
help="User-defined Trinity installation path (binary directory)")
parser.add_argument(
"-m",
"--with_maker",
dest="with_maker",
nargs='?',
help="User-defined Maker installation path (binary directory)")
parser.add_argument(
"-R",
"--with_repeat_modeler",
dest="with_repeat_modeler",
nargs='?',
help="User-defined Repeat Modeler installation path (binary directory)"
)
parser.add_argument(
"-b",
"--with_braker1",
dest="with_braker1",
nargs='?',
help="User-defined Braker1 installation path (binary directory)")
parser.add_argument(
"-B",
"--with_busco",
dest="with_busco",
nargs='?',
help="User-defined BUSCO installation path (binary directory)")
parser.add_argument(
"-i",
"--with_interproscan",
dest="with_interproscan",
nargs='?',
help="User-defined InterproScan installation path (binary directory)")
parser.add_argument('-v',
'--version',
action='version',
version='%(prog)s {}'.format(__version__))
# Options for non-fungus genome
parser.add_argument(
'--no_braker_fungus',
dest='no_braker_fungus',
action='store_true',
help='No --fungus flag in BRAKER for non-fungus genomes')
parser.add_argument(
'--no_jaccard_clip',
dest='no_jaccard_clip',
action='store_true',
help='No --jaccard_clip flag in Trinity for non-fungus genomes')
parser.add_argument(
'--no_genemark_fungus',
dest='no_genemark_fungus',
action='store_true',
help='No --fungus flag in GeneMark for non-fungus genomes')
parser.add_argument("-M",
"--max_intron",
dest="max_intron",
nargs='?',
help="Max intron length (Default: 2,000 bp)")
args = parser.parse_args()
if args.output_dir:
output_dir = os.path.abspath(args.output_dir[0])
else:
print '[ERROR] Please provide OUTPUT DIRECTORY'
sys.exit(2)
if args.trans_read_1:
trans_read_1 = os.path.abspath(args.trans_read_1)
else:
trans_read_1 = ""
if args.trans_read_2:
trans_read_2 = os.path.abspath(args.trans_read_2)
else:
trans_read_2 = ""
if args.trans_read_single:
trans_read_single = os.path.abspath(args.trans_read_single)
else:
trans_read_single = ""
if args.trans_bam:
trans_bam = os.path.abspath(args.trans_bam)
else:
trans_bam = ""
if args.project_name:
project_name = args.project_name[0]
else:
print '[ERROR] Please provide PROJECT NAME'
sys.exit(2)
if args.genome_assembly:
genome_assembly = os.path.abspath(args.genome_assembly[0])
else:
print '[ERROR] Please provide GENOME ASSEMBLY FILE'
sys.exit(2)
if args.augustus_species:
augustus_species = args.augustus_species[0]
else:
print '[ERROR] Please provide AUGUSTUS SPECIES'
sys.exit(2)
if args.org_id:
org_id = args.org_id[0]
else:
print '[ERROR] Please provide ORGANISM ID'
sys.exit(2)
if args.sister_proteome:
sister_proteome = os.path.abspath(args.sister_proteome[0])
else:
print '[ERROR] Please provide SISTER PROTEOME FILE'
sys.exit(2)
if args.num_cores:
num_cores = args.num_cores[0]
else:
num_cores = 1
if args.with_hisat2:
with_hisat2 = os.path.abspath(args.with_hisat2)
else:
with_hisat2 = ''
if args.with_trinity:
with_trinity = os.path.abspath(args.with_trinity)
else:
with_trinity = ''
if args.with_maker:
with_maker = os.path.abspath(args.with_maker)
else:
with_maker = ''
if args.with_repeat_modeler:
with_repeat_modeler = os.path.abspath(args.with_repeat_modeler)
else:
with_repeat_modeler = ''
if args.with_braker1:
with_braker1 = os.path.abspath(args.with_braker1)
else:
with_braker1 = ''
if args.with_busco:
with_busco = os.path.abspath(args.with_busco)
else:
with_busco = ''
if args.with_interproscan:
with_interproscan = os.path.abspath(args.with_interproscan)
else:
with_interproscan = ''
# For non-fungus genomes
if args.no_braker_fungus:
no_braker_fungus = ''
else:
no_braker_fungus = '--fungus'
if args.no_jaccard_clip:
no_jaccard_clip = ''
else:
no_jaccard_clip = '--jaccard_clip'
if args.no_genemark_fungus:
no_genemark_fungus = ''
else:
no_genemark_fungus = '--gmes_fungus'
if args.max_intron:
max_intron = int(args.max_intron)
else:
max_intron = 2000
# Create nessasary dirs
create_dir(output_dir)
# Set logging
log_file = os.path.join(output_dir, 'logs', 'pipeline', 'fungap.log')
global logger_time, logger_txt
logger_time, logger_txt = set_logging(log_file)
logger_txt.debug("\n============ New Run %s ============" %
(datetime.now()))
# Run functions :) Slow is as good as Fast
trans_read_files = check_inputs(trans_read_1, trans_read_2,
trans_read_single, trans_bam,
genome_assembly, sister_proteome)
config_file = run_check_dependencies(output_dir, with_hisat2, with_trinity,
with_maker, with_repeat_modeler,
with_braker1, with_busco,
with_interproscan)
trans_bams = run_hisat2(genome_assembly, trans_read_files, output_dir,
num_cores, config_file, max_intron)
trinity_asms = run_trinity(trans_bams, output_dir, project_name, num_cores,
config_file, no_jaccard_clip, max_intron)
repeat_model_file = run_repeat_modeler(genome_assembly, output_dir,
project_name, num_cores,
config_file)
maker_gff3s, maker_faas = run_maker(genome_assembly, output_dir,
augustus_species, project_name,
sister_proteome, num_cores,
repeat_model_file, trinity_asms,
config_file, no_genemark_fungus)
# Get masked assembly
masked_assembly = os.path.join(output_dir, 'gpre_maker',
'masked_assembly.fasta')
# Run Augustus
augustus_gff3, augustus_faa = run_augustus(masked_assembly, output_dir,
augustus_species)
# Run Braker1
braker1_gff3s, braker1_faas = run_braker1(masked_assembly, trans_bams,
output_dir, num_cores,
config_file, no_braker_fungus)
# Run BUSCO on each gene models
if not glob(os.path.join(output_dir, 'gpre_busco')):
os.mkdir(os.path.join(output_dir, 'gpre_busco'))
for maker_faa in maker_faas:
maker_prefix = os.path.basename(maker_faa).split('.')[0]
maker_busco = os.path.join(output_dir, 'gpre_busco', maker_prefix)
run_busco(maker_faa, maker_busco, num_cores, config_file)
augustus_prefix = os.path.basename(augustus_faa).split('.')[0]
augustus_busco = os.path.join(output_dir, 'gpre_busco', augustus_prefix)
run_busco(augustus_faa, augustus_busco, num_cores, config_file)
for braker1_faa in braker1_faas:
braker1_prefix = os.path.basename(braker1_faa).split('.')[0]
braker1_busco = os.path.join(output_dir, 'gpre_busco', braker1_prefix)
run_busco(braker1_faa, braker1_busco, num_cores, config_file)
busco_dir = os.path.join(output_dir, 'gpre_busco')
# Get protein nr by removing identical proteins
all_prot_files = maker_faas + [augustus_faa] + braker1_faas
nr_prot_file, nr_prot_mapping_file = make_nr_prot(all_prot_files,
output_dir)
# Run BLASTp with nr prot file
blastp_output = run_blastp(nr_prot_file, output_dir, sister_proteome,
num_cores)
# Run IPRscan with nr prot file
ipr_output = run_iprscan(nr_prot_file, output_dir, config_file)
# Get transcripts
transcript_dir = os.path.join(output_dir, 'gpre_filtered', 'transcript')
if not os.path.exists(transcript_dir):
os.mkdir(transcript_dir)
trinity_asm = os.path.join(transcript_dir, 'trinity_transcripts.fna')
command = 'cat %s > %s' % (' '.join(trinity_asms), trinity_asm)
logger_txt.debug('Create transcript')
logger_txt.debug('[Run] %s' % (command))
os.system(command)
augustus_transcript = make_transcripts(genome_assembly, augustus_gff3,
transcript_dir, augustus_prefix)
run_blastn(augustus_transcript, trinity_asm, output_dir, augustus_prefix)
for maker_gff3 in maker_gff3s:
maker_prefix = os.path.basename(maker_gff3).split('.')[0]
maker_transcript = make_transcripts(genome_assembly, maker_gff3,
transcript_dir, maker_prefix)
run_blastn(maker_transcript, trinity_asm, output_dir, maker_prefix)
for braker1_gff3 in braker1_gff3s:
braker1_prefix = os.path.basename(braker1_gff3).split('.')[0]
braker1_transcript = make_transcripts(genome_assembly, braker1_gff3,
transcript_dir, braker1_prefix)
run_blastn(braker1_transcript, trinity_asm, output_dir, braker1_prefix)
# Import BLAST, BUSCO and Pfam score
blast_dict_score, blast_dict_evalue = import_blast(blastp_output,
nr_prot_mapping_file)
busco_dict_score, busco_dict_list = import_busco(busco_dir)
pfam_dict_score, pfam_dict_count = import_pfam(ipr_output,
nr_prot_mapping_file)
blastn_dict = import_blastn(transcript_dir)
# Catch bad genes
D_bad_pickle = catch_bad_genes(maker_gff3s, augustus_gff3, braker1_gff3s,
genome_assembly, output_dir)
filter_gff3s(maker_gff3s, augustus_gff3, braker1_gff3s, blast_dict_score,
blast_dict_evalue, busco_dict_score, busco_dict_list,
pfam_dict_score, pfam_dict_count, blastn_dict, D_bad_pickle,
nr_prot_file, nr_prot_mapping_file, org_id, output_dir)
# Copy output files
copy_output(output_dir)
# Create markdown
create_markdown(genome_assembly, output_dir, trinity_asms)